Face snapshot gunlock load balancing method

Abstract

The invention relates to the technical field of face recognition, in particular to a face snapshot gunlock load balancing method, which comprises the steps that two paths of original images are acquired, and an acquisition module of a snapshot gunlock transmits the original images to an image encoding and decoding module; an image encoding and decoding module outputs one path to a CPU encoding module for encoding, and outputs the other path to the GPU module for face detection; after receiving the image, a CPU image application module stores the image to a local storage card and uploads the image to a far-end server through a network; a CPU image analysis module analyzes the locally stored images, counts the number N of face snapshots in a set time and transmits a code rate value X needingto be adjusted, and the CPU encoding module acquires and configures an initial code rate value as the adjusted code rate value X; the coding code rate is dynamically adjusted in real time, the code rate is reduced when the snapshot amount is large, and the effects of giving way to CPU resources, locally storing pictures and uploading the pictures to a remote server are achieved; on the contrary,the code rate can be recovered and even improved in the time period with small snapshot amount, and a load balancing strategy is achieved.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a load balancing method for a face capture camera. Background technique [0002] In recent years, with the popularity of artificial intelligence chips, face capture cameras have gradually become an indispensable product in the security field. In view of the limited resources of embedded devices (such as memory, GPU, CPU processing power), how to make full use of the limited It has become a key technology to maximize the performance of the face capture trigger. The face capture trigger is characterized by face capture, and its equipment resources must prioritize the local storage of captured pictures and the remote server upload of captured pictures. [0003] In traditional bolt-action applications, the encoding rate is usually limited to a static parameter, and installation and commissioning personnel can determine an initial value based on experience, combined with app...

AI Technical Summary

Problems solved by technology

If this fixed bit rate is set too small, it will lead to unclear video stream and waste of device resources; if it is set too high, it will cause image frame loss and overload work of the device. Based on this, how to pass statistics on the current The number of face captures can be dynamically adjusted in real time, and the bit rate can be reduced during periods of large amount of captures, allowing CPU resources to be stored locally and network bandwidth to be uploaded to remote servers. The bit rate can be restored or even increased during the time period when the amount of capture is small, so as to achieve a load balancing strategy

Images